Introduce IBlock and ILettersBlock interfaces

src/UglyToad.PdfPig.DocumentLayoutAnalysis/Export/AltoXmlTextExporter.cs

@@ -219,7 +219,7 @@ private AltoDocument.AltoGraphicalElement ToAltoGraphicalElement(PdfPath pdfPath
         private AltoDocument.AltoIllustration ToAltoIllustration(IPdfImage pdfImage, double height)
         {
             illustrationCount++;
-            var rectangle = pdfImage.Bounds;
+            var rectangle = pdfImage.BoundingBox;
 
             return new AltoDocument.AltoIllustration
             {

src/UglyToad.PdfPig.DocumentLayoutAnalysis/Export/HOcrTextExporter.cs

@@ -273,7 +273,7 @@ private string GetCode(PdfPath path, double pageHeight, bool subPaths, int level
         private string GetCode(IPdfImage pdfImage, double pageHeight, int level)
         {
             imageCount++;
-            var bbox = pdfImage.Bounds;
+            var bbox = pdfImage.BoundingBox;
             return GetIndent(level) + "<span class='ocr_image' id='image_" + pageCount + "_"
                             + imageCount + "' title='" + GetCode(bbox, pageHeight) + "' />";
         }

src/UglyToad.PdfPig.DocumentLayoutAnalysis/Export/PageXmlTextExporter.cs

@@ -273,7 +273,7 @@ private PageXmlDocument.PageXmlLineDrawingRegion ToPageXmlLineDrawingRegion(PdfP
         private PageXmlDocument.PageXmlImageRegion ToPageXmlImageRegion(IPdfImage pdfImage, PageXmlData data, double pageWidth, double pageHeight)
         {
             data.RegionsCount++;
-            var bbox = pdfImage.Bounds;
+            var bbox = pdfImage.BoundingBox;
             return new PageXmlDocument.PageXmlImageRegion()
             {
                 Coords = ToCoords(bbox, pageWidth, pageHeight),

src/UglyToad.PdfPig.DocumentLayoutAnalysis/TextBlock.cs

@@ -9,8 +9,13 @@
     /// <summary>
     /// A block of text.
     /// </summary>
-    public class TextBlock
-    {
+    public class TextBlock: ILettersBlock
+    {       
+        /// <summary>
+        /// The letters contained in this TextBlock
+        /// </summary>
+        public IReadOnlyList<Letter> Letters { get; }
+
         /// <summary>
         /// The separator used between lines in the block.
         /// </summary>
@@ -63,6 +68,7 @@ public TextBlock(IReadOnlyList<TextLine> lines, string separator = "\n")
             ReadingOrder = -1;
 
             TextLines = lines;
+            Letters = lines.SelectMany(tl => tl.Words).SelectMany(w => w.Letters).ToList().AsReadOnly();
 
             if (lines.Count == 1)
             {

src/UglyToad.PdfPig.DocumentLayoutAnalysis/TextLine.cs

@@ -9,8 +9,13 @@
     /// <summary>
     /// A line of text.
     /// </summary>
-    public class TextLine
+    public class TextLine : ILettersBlock
     {
+        /// <summary>
+        /// The letters contained in this TextLine
+        /// </summary>
+        public IReadOnlyList<Letter> Letters { get; }
+
         /// <summary>
         /// The separator used between words in the line.
         /// </summary>
@@ -56,6 +61,7 @@ public TextLine(IReadOnlyList<Word> words, string separator = " ")
             Separator = separator;
 
             Words = words;
+            Letters = words.SelectMany(w => w.Letters).ToList().AsReadOnly();
 
             if (Words.Count == 1)
             {

src/UglyToad.PdfPig.DocumentLayoutAnalysis/WhitespaceCoverExtractor.cs

@@ -51,7 +51,7 @@ public static IReadOnlyList<PdfRectangle> GetWhitespaces(IEnumerable<Word> words
 
             if (images?.Any() == true)
             {
-                bboxes.AddRange(images.Where(w => w.Bounds.Width > 0 && w.Bounds.Height > 0).Select(o => o.Bounds));
+                bboxes.AddRange(images.Where(w => w.BoundingBox.Width > 0 && w.BoundingBox.Height > 0).Select(o => o.BoundingBox));
             }
 
             return GetWhitespaces(bboxes,

src/UglyToad.PdfPig.Tests/Integration/SinglePageLibreOfficeImages.cs

@@ -26,29 +26,29 @@ public void ImagesHaveCorrectDimensionsAndLocations()
             {
                 var page = document.GetPage(1);
 
-                var images = page.GetImages().OrderBy(x => x.Bounds.Width).ToList();
+                var images = page.GetImages().OrderBy(x => x.BoundingBox.Width).ToList();
 
                 var pdfPigSquare = images[0];
 
-                Assert.Equal(148.3d, pdfPigSquare.Bounds.Width, doubleComparer);
-                Assert.Equal(148.3d, pdfPigSquare.Bounds.Height, doubleComparer);
-                Assert.Equal(60.1d, pdfPigSquare.Bounds.Left, doubleComparer);
-                Assert.Equal(765.8d, pdfPigSquare.Bounds.Top, doubleComparer);
+                Assert.Equal(148.3d, pdfPigSquare.BoundingBox.Width, doubleComparer);
+                Assert.Equal(148.3d, pdfPigSquare.BoundingBox.Height, doubleComparer);
+                Assert.Equal(60.1d, pdfPigSquare.BoundingBox.Left, doubleComparer);
+                Assert.Equal(765.8d, pdfPigSquare.BoundingBox.Top, doubleComparer);
 
 
                 var pdfPigSquished = images[1];
 
-                Assert.Equal(206.8d, pdfPigSquished.Bounds.Width, doubleComparer);
-                Assert.Equal(83.2d, pdfPigSquished.Bounds.Height, doubleComparer);
-                Assert.Equal(309.8d, pdfPigSquished.Bounds.Left, doubleComparer);
-                Assert.Equal(552.1d, pdfPigSquished.Bounds.Top, doubleComparer);
+                Assert.Equal(206.8d, pdfPigSquished.BoundingBox.Width, doubleComparer);
+                Assert.Equal(83.2d, pdfPigSquished.BoundingBox.Height, doubleComparer);
+                Assert.Equal(309.8d, pdfPigSquished.BoundingBox.Left, doubleComparer);
+                Assert.Equal(552.1d, pdfPigSquished.BoundingBox.Top, doubleComparer);
 
                 var birthdayPigs = images[2];
 
-                Assert.Equal(391d, birthdayPigs.Bounds.Width, doubleComparer);
-                Assert.Equal(267.1d, birthdayPigs.Bounds.Height, doubleComparer);
-                Assert.Equal(102.2d, birthdayPigs.Bounds.Left, doubleComparer);
-                Assert.Equal(426.3d, birthdayPigs.Bounds.Top, doubleComparer);
+                Assert.Equal(391d, birthdayPigs.BoundingBox.Width, doubleComparer);
+                Assert.Equal(267.1d, birthdayPigs.BoundingBox.Height, doubleComparer);
+                Assert.Equal(102.2d, birthdayPigs.BoundingBox.Left, doubleComparer);
+                Assert.Equal(426.3d, birthdayPigs.BoundingBox.Top, doubleComparer);
             }
         }
 

src/UglyToad.PdfPig.Tests/PublicApiScannerTests.cs

@@ -77,6 +77,8 @@ public void OnlyExposedApiIsPublic()
                 "UglyToad.PdfPig.Content.DocumentInformation",
                 "UglyToad.PdfPig.Content.EmbeddedFile",
                 "UglyToad.PdfPig.Content.Hyperlink",
+                "UglyToad.PdfPig.Content.IBoundingBox",
+                "UglyToad.PdfPig.Content.ILettersBlock",
                 "UglyToad.PdfPig.Content.InlineImage",
                 "UglyToad.PdfPig.Content.IPageFactory`1",
                 "UglyToad.PdfPig.Content.IPdfImage",

src/UglyToad.PdfPig.Tests/TestPdfImage.cs

@@ -9,7 +9,7 @@
 
     public class TestPdfImage : IPdfImage
     {
-        public PdfRectangle Bounds { get; set; }
+        public PdfRectangle BoundingBox { get; set; }
 
         public int WidthInSamples { get; set; }
 

src/UglyToad.PdfPig.Tests/Writer/PdfDocumentBuilderTests.cs

@@ -563,8 +563,8 @@ public void CanWriteSinglePageWithJpeg()
 
                 Assert.NotNull(image);
 
-                Assert.Equal(expectedBounds.BottomLeft, image.Bounds.BottomLeft);
-                Assert.Equal(expectedBounds.TopRight, image.Bounds.TopRight);
+                Assert.Equal(expectedBounds.BottomLeft, image.BoundingBox.BottomLeft);
+                Assert.Equal(expectedBounds.TopRight, image.BoundingBox.TopRight);
 
                 Assert.Equal(imageBytes, image.RawMemory.ToArray());
             }
@@ -609,18 +609,18 @@ public void CanWrite2PagesSharingJpeg()
                 Assert.Equal(2, page1Images.Count);
 
                 var image1 = page1Images[0];
-                Assert.Equal(expectedBounds1, image1.Bounds);
+                Assert.Equal(expectedBounds1, image1.BoundingBox);
 
                 var image2 = page1Images[1];
-                Assert.Equal(expectedBounds2, image2.Bounds);
+                Assert.Equal(expectedBounds2, image2.BoundingBox);
 
                 var page2Doc = document.GetPage(2);
 
                 var image3 = Assert.Single(page2Doc.GetImages());
 
                 Assert.NotNull(image3);
 
-                Assert.Equal(expectedBounds3, image3.Bounds);
+                Assert.Equal(expectedBounds3, image3.BoundingBox);
 
                 Assert.Equal(imageBytes, image1.RawMemory.ToArray());
                 Assert.Equal(imageBytes, image2.RawMemory.ToArray());
@@ -696,8 +696,8 @@ public void CanWriteSinglePageWithPng()
 
                 Assert.NotNull(image);
 
-                Assert.Equal(expectedBounds.BottomLeft, image.Bounds.BottomLeft);
-                Assert.Equal(expectedBounds.TopRight, image.Bounds.TopRight);
+                Assert.Equal(expectedBounds.BottomLeft, image.BoundingBox.BottomLeft);
+                Assert.Equal(expectedBounds.TopRight, image.BoundingBox.TopRight);
 
                 Assert.True(image.TryGetPng(out var png));
                 Assert.NotNull(png);

src/UglyToad.PdfPig/Content/IBoundingBox.cs

@@ -0,0 +1,36 @@
+namespace UglyToad.PdfPig.Content
+{
+    using UglyToad.PdfPig.Core;
+
+    /// <summary>
+    /// Interface for classes with a bounding box
+    /// </summary>
+    public interface IBoundingBox
+    {
+        /// <summary>
+        /// Gets the Bounding Box: The rectangle completely containing this object
+        /// </summary>
+        PdfRectangle BoundingBox { get; }
+    }
+
+    /// <summary>
+    /// Interface for classes with a bounding box and text
+    /// </summary>
+    public interface ILettersBlock : IBoundingBox
+    {
+        /// <summary>
+        /// The text of the block
+        /// </summary>
+        string Text { get; }
+
+        /// <summary>
+        /// Text orientation of the block.
+        /// </summary>
+        TextOrientation TextOrientation { get; }
+
+        /// <summary>
+        /// The letters contained in the Block
+        /// </summary>
+        IReadOnlyList<Letter> Letters { get; }
+    }
+}

src/UglyToad.PdfPig/Content/IPdfImage.cs

@@ -12,13 +12,8 @@
     /// <summary>
     /// An image in a PDF document, may be an <see cref="InlineImage"/> or a PostScript image XObject (<see cref="XObjectImage"/>).
     /// </summary>
-    public interface IPdfImage
+    public interface IPdfImage : IBoundingBox
     {
-        /// <summary>
-        /// The placement rectangle of the image in PDF coordinates.
-        /// </summary>
-        PdfRectangle Bounds { get; }
-
         /// <summary>
         /// The width of the image in samples.
         /// </summary>

src/UglyToad.PdfPig/Content/InlineImage.cs

@@ -19,7 +19,7 @@ public class InlineImage : IPdfImage
         private readonly Lazy<ReadOnlyMemory<byte>>? memoryFactory;
 
         /// <inheritdoc />
-        public PdfRectangle Bounds { get; }
+        public PdfRectangle BoundingBox { get; }
 
         /// <inheritdoc />
         public int WidthInSamples { get; }
@@ -69,7 +69,7 @@ internal InlineImage(PdfRectangle bounds, int widthInSamples, int heightInSample
             DictionaryToken streamDictionary,
             ColorSpaceDetails colorSpaceDetails)
         {
-            Bounds = bounds;
+            BoundingBox = bounds;
             WidthInSamples = widthInSamples;
             HeightInSamples = heightInSamples;
             Decode = decode;
@@ -124,7 +124,7 @@ public bool TryGetBytesAsMemory(out ReadOnlyMemory<byte> bytes)
         /// <inheritdoc />
         public override string ToString()
         {
-            return $"Inline Image (w {Bounds.Width}, h {Bounds.Height})";
+            return $"Inline Image (w {BoundingBox.Width}, h {BoundingBox.Height})";
         }
     }
 }

src/UglyToad.PdfPig/Content/Letter.cs

@@ -7,12 +7,12 @@
     /// <summary>
     /// A glyph or combination of glyphs (characters) drawn by a PDF content stream.
     /// </summary>
-    public class Letter
-    {
+    public class Letter : IBoundingBox
+    {
         /// <summary>
         /// The text for this letter or unicode character.
         /// </summary>
-        public string Value { get; }
+        public string Value { get; }
 
         /// <summary>
         /// Text orientation of the letter.
@@ -44,7 +44,12 @@ public class Letter
         /// For example letters with descenders, p, j, etc., will have a box extending below the <see cref="Location"/> they are placed at.
         /// The width of the glyph may also be more or less than the <see cref="Width"/> allocated for the character in the PDF content.
         /// </summary>
-        public PdfRectangle GlyphRectangle { get; }
+        public PdfRectangle GlyphRectangle { get; }
+
+        /// <summary>
+        /// Gets the Bounding Box: The rectangle completely containing this object. Same as <see cref="GlyphRectangle"/>
+        /// </summary>
+        public PdfRectangle BoundingBox => GlyphRectangle;
 
         /// <summary>
         /// Size as defined in the PDF file. This is not equivalent to font size in points but is relative to other font sizes on the page.

src/UglyToad.PdfPig/Content/Word.cs

@@ -9,7 +9,7 @@
     /// <summary>
     /// A word.
     /// </summary>
-    public class Word
+    public class Word : ILettersBlock
     {
         /// <summary>
         /// The text of the word.

src/UglyToad.PdfPig/XObjects/XObjectImage.cs

@@ -19,7 +19,7 @@ public class XObjectImage : IPdfImage
         private readonly Lazy<ReadOnlyMemory<byte>>? memoryFactory;
 
         /// <inheritdoc />
-        public PdfRectangle Bounds { get; }
+        public PdfRectangle BoundingBox { get; }
 
         /// <inheritdoc />
         public int WidthInSamples { get; }
@@ -81,7 +81,7 @@ internal XObjectImage(PdfRectangle bounds,
             Lazy<ReadOnlyMemory<byte>>? bytes,
             ColorSpaceDetails? colorSpaceDetails)
         {
-            Bounds = bounds;
+            BoundingBox = bounds;
             WidthInSamples = widthInSamples;
             HeightInSamples = heightInSamples;
             BitsPerComponent = bitsPerComponent;
@@ -116,7 +116,7 @@ public bool TryGetBytesAsMemory(out ReadOnlyMemory<byte> bytes)
         /// <inheritdoc />
         public override string ToString()
         {
-            return $"XObject Image (w {Bounds.Width}, h {Bounds.Height}): {ImageDictionary}";
+            return $"XObject Image (w {BoundingBox.Width}, h {BoundingBox.Height}): {ImageDictionary}";
         }
     }
 }